EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-Speech
This work addresses the need for more nuanced emotional control in TTS systems for applications like human-computer interaction, though it is incremental as it builds on existing emotional TTS methods.
The paper tackled the problem of limited emotional control in text-to-speech systems, which typically use predefined emotion labels, by proposing EmoSphere-TTS that uses a spherical emotion vector to model emotional style and intensity, resulting in high-quality expressive speech synthesis.
Despite rapid advances in the field of emotional text-to-speech (TTS), recent studies primarily focus on mimicking the average style of a particular emotion. As a result, the ability to manipulate speech emotion remains constrained to several predefined labels, compromising the ability to reflect the nuanced variations of emotion. In this paper, we propose EmoSphere-TTS, which synthesizes expressive emotional speech by using a spherical emotion vector to control the emotional style and intensity of the synthetic speech. Without any human annotation, we use the arousal, valence, and dominance pseudo-labels to model the complex nature of emotion via a Cartesian-spherical transformation. Furthermore, we propose a dual conditional adversarial network to improve the quality of generated speech by reflecting the multi-aspect characteristics. The experimental results demonstrate the model ability to control emotional style and intensity with high-quality expressive speech.